Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
51519e40
Commit
51519e40
authored
Jun 25, 2024
by
haileyschoelkopf
Browse files
add many explicit group configs
parent
44a602ab
Changes
33
Show whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
5 additions
and
57 deletions
+5
-57
lm_eval/tasks/agieval/agieval.yaml
lm_eval/tasks/agieval/agieval.yaml
+1
-1
lm_eval/tasks/agieval/agieval_cn.yaml
lm_eval/tasks/agieval/agieval_cn.yaml
+1
-1
lm_eval/tasks/agieval/agieval_en.yaml
lm_eval/tasks/agieval/agieval_en.yaml
+2
-2
lm_eval/tasks/agieval/agieval_nous.yaml
lm_eval/tasks/agieval/agieval_nous.yaml
+1
-1
lm_eval/tasks/agieval/aqua-rat.yaml
lm_eval/tasks/agieval/aqua-rat.yaml
+0
-4
lm_eval/tasks/agieval/gaokao-biology.yaml
lm_eval/tasks/agieval/gaokao-biology.yaml
+0
-3
lm_eval/tasks/agieval/gaokao-chemistry.yaml
lm_eval/tasks/agieval/gaokao-chemistry.yaml
+0
-3
lm_eval/tasks/agieval/gaokao-chinese.yaml
lm_eval/tasks/agieval/gaokao-chinese.yaml
+0
-3
lm_eval/tasks/agieval/gaokao-english.yaml
lm_eval/tasks/agieval/gaokao-english.yaml
+0
-3
lm_eval/tasks/agieval/gaokao-geography.yaml
lm_eval/tasks/agieval/gaokao-geography.yaml
+0
-3
lm_eval/tasks/agieval/gaokao-history.yaml
lm_eval/tasks/agieval/gaokao-history.yaml
+0
-3
lm_eval/tasks/agieval/gaokao-mathcloze.yaml
lm_eval/tasks/agieval/gaokao-mathcloze.yaml
+0
-3
lm_eval/tasks/agieval/gaokao-mathqa.yaml
lm_eval/tasks/agieval/gaokao-mathqa.yaml
+0
-3
lm_eval/tasks/agieval/gaokao-physics.yaml
lm_eval/tasks/agieval/gaokao-physics.yaml
+0
-3
lm_eval/tasks/agieval/jec-qa-ca.yaml
lm_eval/tasks/agieval/jec-qa-ca.yaml
+0
-3
lm_eval/tasks/agieval/jec-qa-kd.yaml
lm_eval/tasks/agieval/jec-qa-kd.yaml
+0
-3
lm_eval/tasks/agieval/logiqa-en.yaml
lm_eval/tasks/agieval/logiqa-en.yaml
+0
-4
lm_eval/tasks/agieval/logiqa-zh.yaml
lm_eval/tasks/agieval/logiqa-zh.yaml
+0
-3
lm_eval/tasks/agieval/lsat-ar.yaml
lm_eval/tasks/agieval/lsat-ar.yaml
+0
-4
lm_eval/tasks/agieval/lsat-lr.yaml
lm_eval/tasks/agieval/lsat-lr.yaml
+0
-4
No files found.
lm_eval/tasks/agieval/agieval.yaml
View file @
51519e40
...
@@ -21,7 +21,7 @@ task:
...
@@ -21,7 +21,7 @@ task:
-
agieval_sat_en_without_passage
-
agieval_sat_en_without_passage
-
agieval_sat_en
-
agieval_sat_en
-
agieval_sat_math
-
agieval_sat_math
aggregate_metric
:
aggregate_metric
_list
:
-
metric
:
acc
-
metric
:
acc
aggregation
:
mean
aggregation
:
mean
weight_by_size
:
true
weight_by_size
:
true
...
...
lm_eval/tasks/agieval/agieval_cn.yaml
View file @
51519e40
...
@@ -11,7 +11,7 @@ task:
...
@@ -11,7 +11,7 @@ task:
-
agieval_jec_qa_ca
-
agieval_jec_qa_ca
-
agieval_jec_qa_kd
-
agieval_jec_qa_kd
-
agieval_logiqa_zh
-
agieval_logiqa_zh
aggregate_metric
:
aggregate_metric
_list
:
-
metric
:
acc
-
metric
:
acc
aggregation
:
mean
aggregation
:
mean
weight_by_size
:
true
weight_by_size
:
true
...
...
lm_eval/tasks/agieval/agieval_en.yaml
View file @
51519e40
group
:
agieval_en
group
:
agieval_en
task
:
task
:
-
agieval_aqua_rat
-
agieval_aqua_rat
-
agieval_gaokao_english
-
agieval_gaokao_english
# categorizing as EN because the AGIEval codebase lists this as in `english_qa_tasks`
-
agieval_logiqa_en
-
agieval_logiqa_en
-
agieval_lsat_ar
-
agieval_lsat_ar
-
agieval_lsat_lr
-
agieval_lsat_lr
...
@@ -10,7 +10,7 @@ task:
...
@@ -10,7 +10,7 @@ task:
-
agieval_sat_en_without_passage
-
agieval_sat_en_without_passage
-
agieval_sat_en
-
agieval_sat_en
-
agieval_sat_math
-
agieval_sat_math
aggregate_metric
:
aggregate_metric
_list
:
-
metric
:
acc
-
metric
:
acc
aggregation
:
mean
aggregation
:
mean
weight_by_size
:
true
weight_by_size
:
true
...
...
lm_eval/tasks/agieval/agieval_nous.yaml
View file @
51519e40
...
@@ -8,7 +8,7 @@ task:
...
@@ -8,7 +8,7 @@ task:
-
agieval_sat_en_without_passage
-
agieval_sat_en_without_passage
-
agieval_sat_en
-
agieval_sat_en
-
agieval_sat_math
-
agieval_sat_math
aggregate_metric
:
aggregate_metric
_list
:
-
metric
:
acc_norm
-
metric
:
acc_norm
aggregation
:
mean
aggregation
:
mean
weight_by_size
:
true
weight_by_size
:
true
...
...
lm_eval/tasks/agieval/aqua-rat.yaml
View file @
51519e40
group
:
-
agieval
-
agieval_en
-
agieval_nous
task
:
agieval_aqua_rat
task
:
agieval_aqua_rat
dataset_path
:
hails/agieval-aqua-rat
dataset_path
:
hails/agieval-aqua-rat
dataset_name
:
null
dataset_name
:
null
...
...
lm_eval/tasks/agieval/gaokao-biology.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_gaokao_biology
task
:
agieval_gaokao_biology
dataset_path
:
hails/agieval-gaokao-biology
dataset_path
:
hails/agieval-gaokao-biology
lm_eval/tasks/agieval/gaokao-chemistry.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_gaokao_chemistry
task
:
agieval_gaokao_chemistry
dataset_path
:
hails/agieval-gaokao-chemistry
dataset_path
:
hails/agieval-gaokao-chemistry
lm_eval/tasks/agieval/gaokao-chinese.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_gaokao_chinese
task
:
agieval_gaokao_chinese
dataset_path
:
hails/agieval-gaokao-chinese
dataset_path
:
hails/agieval-gaokao-chinese
lm_eval/tasks/agieval/gaokao-english.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_en
# categorizing as EN because the AGIEval codebase lists this as in `english_qa_tasks`
task
:
agieval_gaokao_english
task
:
agieval_gaokao_english
dataset_path
:
hails/agieval-gaokao-english
dataset_path
:
hails/agieval-gaokao-english
lm_eval/tasks/agieval/gaokao-geography.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_gaokao_geography
task
:
agieval_gaokao_geography
dataset_path
:
hails/agieval-gaokao-geography
dataset_path
:
hails/agieval-gaokao-geography
lm_eval/tasks/agieval/gaokao-history.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_gaokao_history
task
:
agieval_gaokao_history
dataset_path
:
hails/agieval-gaokao-history
dataset_path
:
hails/agieval-gaokao-history
lm_eval/tasks/agieval/gaokao-mathcloze.yaml
View file @
51519e40
group
:
-
agieval
-
agieval_cn
task
:
agieval_gaokao_mathcloze
task
:
agieval_gaokao_mathcloze
dataset_path
:
hails/agieval-gaokao-mathcloze
dataset_path
:
hails/agieval-gaokao-mathcloze
dataset_name
:
null
dataset_name
:
null
...
...
lm_eval/tasks/agieval/gaokao-mathqa.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_gaokao_mathqa
task
:
agieval_gaokao_mathqa
dataset_path
:
hails/agieval-gaokao-mathqa
dataset_path
:
hails/agieval-gaokao-mathqa
lm_eval/tasks/agieval/gaokao-physics.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_gaokao_physics
task
:
agieval_gaokao_physics
dataset_path
:
hails/agieval-gaokao-physics
dataset_path
:
hails/agieval-gaokao-physics
lm_eval/tasks/agieval/jec-qa-ca.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_jec_qa_ca
task
:
agieval_jec_qa_ca
dataset_path
:
hails/agieval-jec-qa-ca
dataset_path
:
hails/agieval-jec-qa-ca
lm_eval/tasks/agieval/jec-qa-kd.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_jec_qa_kd
task
:
agieval_jec_qa_kd
dataset_path
:
hails/agieval-jec-qa-kd
dataset_path
:
hails/agieval-jec-qa-kd
lm_eval/tasks/agieval/logiqa-en.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_nous
-
agieval_en
task
:
agieval_logiqa_en
task
:
agieval_logiqa_en
dataset_path
:
hails/agieval-logiqa-en
dataset_path
:
hails/agieval-logiqa-en
lm_eval/tasks/agieval/logiqa-zh.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_cn
task
:
agieval_logiqa_zh
task
:
agieval_logiqa_zh
dataset_path
:
hails/agieval-logiqa-zh
dataset_path
:
hails/agieval-logiqa-zh
lm_eval/tasks/agieval/lsat-ar.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_nous
-
agieval_en
task
:
agieval_lsat_ar
task
:
agieval_lsat_ar
dataset_path
:
hails/agieval-lsat-ar
dataset_path
:
hails/agieval-lsat-ar
lm_eval/tasks/agieval/lsat-lr.yaml
View file @
51519e40
include
:
aqua-rat.yaml
include
:
aqua-rat.yaml
group
:
-
agieval
-
agieval_nous
-
agieval_en
task
:
agieval_lsat_lr
task
:
agieval_lsat_lr
dataset_path
:
hails/agieval-lsat-lr
dataset_path
:
hails/agieval-lsat-lr
Prev
1
2
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment